Which model leads EvalPlus?

Kimi K2 Base leads the EvalPlus board of 7 measured models on the Vector Wire tracker at 80.3. Every score is source-attributed with a verification tier.

EvalPlus Leaderboard — Model Scores

Refresh Models —Deals —Regulatory —Sources —

Pro Mode — raw scores, one benchmark under the lensofficial card harness

The field · 7 measured

36.480.3

7 models measured, most on the official card harness. Kimi K2 Base tops the board at 80.3.

7 measured·4 new this week·Lifecycle Updated Sep 2, 2026Basis

#◆Vendor$/M in$/M out

Leader — ignites whiteField — fill cools with scoreIndependently verified only0 of 7Bars show 36.4–80.3· ◆ solid = first-party or better · outlined = arm's-length

01Kimi K2 BaseNEWMoonshot80.3———

02Qwen2 72B InstructNEWAlibaba79———

03Qwen3 235B A22BNEWAlibaba77.6$0.70/M$2.8/M$0.023

04Qwen2 7B InstructNEWAlibaba70.3———

05Llama-3-8BMeta40.3$0.04/M$0.14/M$0.002

06Gemma-7BGoogle39.6———

07Mistral-7BMistral36.4———

◆ solid = independently verified · aggregator attested · vendor attributed — outlined = cross-reference · source-attributed. Dimmed ◆ = confidence inferred. “+N alts” = alternate disclosures in the drawer with why-demoted. Prices per million tokens; $/point = input price ÷ score. Every row opens its model dossier.